Skip to main content
Navigation
Work About Contact
Overview The Problem Process Impact
Hire Me →
UX Case Study 🤖 AI & Machine Learning

Automating Court Transcripts: Deploying Offline AI Under Strict Government Privacy Laws.

External contractors were drowning in manual audio work. Delays stretched to weeks. I designed and built a fully offline AI transcriber that runs on court hardware, generates same-day dirty transcripts, and opens a direct revenue stream without adding headcount.

Role UX Designer
& Developer
Timeline May 2024 -
June 2025
Tools
Python WhisperX Figma
Constraint 100% Offline (No Cloud)

Are you a hiring manager?

Paste your job description and my AI will tell you exactly why I'm a fit.

AI Transcriber App Prototype

The Problem vs. The Solution

Government privacy law ruled out every commercial AI tool on the market. So we built one that never touches the cloud. Turnaround dropped from weeks to hours, and the courts walked away with a revenue stream they didn't have before.

⚠️
Before

The Transcription Backlog

Court clerks were stuck waiting days, sometimes weeks, for external contractors to manually transcribe audio. And every cloud-based AI tool that could have helped? Legally off-limits.

Third-Party Delays
Strained external contractors manually transcribed audio after court sessions, causing error-prone delays of several days to weeks.
🔒
Strict Cloud Restrictions
Due to severe government security and privacy policies, existing commercial cloud-based AI tools (like standard ChatGPT) were strictly prohibited.
📉
No Internal Capabilities
With no first-party transcription services provided by the courts, operational costs soared and clients waited indefinitely for preliminary data.
After

Offline AI Automation

A Python-based desktop app that runs entirely on local hardware, fits into how clerks already work, and spits out a timestamped transcript in hours. No internet required.

🛡️
1. Secure Offline Pipeline
Built a Python-based app using WhisperX with fully offline language models to guarantee 100% compliance with local infrastructure.
🗣️
2. Speaker Diarization
Integrated advanced machine learning to automatically differentiate and label multiple speakers in chaotic court recordings.
💰
3. Same-Day Delivery & Revenue
Outputs a time-accurate 'dirty transcript' within hours, creating a direct monetization path for the government without hiring more staff.

The Agile Evolution

Each sprint addressed a distinct constraint. We started by mapping real friction through stakeholder interviews and low-fidelity wireframes, then designed the offline WhisperX + PyAnnote pipeline to satisfy strict data-security requirements, and finally prototyped the Flet desktop interface that transformed raw speaker-diarized audio into a searchable, timestamped transcript output.

Manual Chaos: The Friction.

Courtroom audio was a black box. Over 100 hours of unindexed recordings sat in storage, requiring clerks to manually scrub through tapes. That process took days and cost requesters $9.25 a page.

  • Unsearchable physical media (USB/Tapes)
  • Prohibitive costs for self-represented litigants
  • Inaccessible legalese in procedural filings
Wireframe 1
Wireframe Concept 1
Wireframe 2
Wireframe Concept 2
Wireframe 3
Wireframe Concept 3
Initial low-fidelity sketches focusing on accessibility patterns

Under The Hood

Running production-grade NLP on government hardware with no internet, no GPU, and strict data rules took some creative problem-solving. Here's what's actually happening under the hood.

✨ Gemini AI Integration

AI Tech Explainer

Curious how WhisperX and speaker diarization actually work without an internet connection? Pick your background and I'll generate an explanation pitched at exactly your level.

Want to see my UX thinking?

Here's how I broke the transcription problem apart: mapping constraints, failure states, and edge cases, packaged into a custom React slide deck.

View Problem-Solving Logic
Live Prototype

Try the AI Transcriber

This is the real thing. Load a file, watch it process, and explore the full output interface, exactly as it was designed and shipped.

Open in new tab

The Business Impact

Going offline-first wasn't a constraint. It was the unlock. Cutting out third-party vendors freed up budget, earned trust from leadership, and gave the courts a new way to generate revenue on their own terms.

0%
Faster Delivery
Hours instead of weeks
0%
Security Compliance
Zero cloud data transmission
+0
New Revenue Stream
Direct client monetization

Transcription Turnaround Time

Days required to generate a preliminary transcript.

Available for Work

Let's build something impactful.

I'm currently open to new opportunities in UX/UI Design, Product Design, and GovTech transformation roles. If you have a legacy nightmare that needs solving, I'd love to chat.